An expository derivation of diffusion models plus a single-dataset experiment showing diffusion-augmented training data improves fraud-detection recall for XGBoost and Random Forest.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Generative Modeling with Diffusion
An expository derivation of diffusion models plus a single-dataset experiment showing diffusion-augmented training data improves fraud-detection recall for XGBoost and Random Forest.